© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13973
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohl
    -0.10
     Daly
    -0.09
    ippy
    -0.09
    rens
    -0.08
    (...)
    -0.08
    AMPL
    -0.08
     Sabb
    -0.08
    ila
    -0.08
     entreprene
    -0.08
     Duy
    -0.08
    POSITIVE LOGITS
    mites
    0.09
     acting
    0.09
    arella
    0.08
    rita
    0.08
    876
    0.08
     hyp
    0.08
     fir
    0.08
    utable
    0.08
     El
    0.08
     Fowler
    0.08
    Activations Density 0.033%

    No Known Activations